Dynamic Replication Strategies for Object Storage Systems

  • Tan Zhipeng
  • Feng Dan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4097)


Object replication is an important and sophisticated question, it can reduce access latency and bandwidth consumption, replication can also help in load balancing and can improve reliability by creating multiple replicas of the same storage object. But there are many difficulties to realize object replication in efficiently. In this paper, we discuss the architecture of object storage system with object replication, and analyze key question of dynamic replication such as replica granularity, When to replicate storage object and Where to place the replicas etc.. In the theory, we give the formulas of these question, the analysis prove these formulas are reasonable.


Object Storage System Dynamic Replication Management Architecture 


  1. 1.
    Mesnier, M., Ganger, G.R., Riedel, E.: Object-Based Storage. IEEE Communications Magazine, 84–90 (August 2003)Google Scholar
  2. 2.
    Holtman, K., van der Stok, P., Willers, I.: Towards Mass Storage Systems with Object Granularity. In: Proc. of the Eighth NASA Goddard Conference on Mass Storage Systems and Technologies, Maryland, USA, March 27-30, pp. 135–149 (2000)Google Scholar
  3. 3.
    Holtman, K., Stockinger, H.: Building a Large Location Table to Find Replicas of Physics Objects. In: Computing in High Energy Physics (CHEP 2000), Italy (February 2000)Google Scholar
  4. 4.
    Holtman, K.: Object Level Physics Data Replication in the Grid. In: VII International Workshop on Advanced Computing and Analysis Techniques in Physics Research ACAT 2000, Chicago, USA, October 16-20 (2000)Google Scholar
  5. 5.
    Chervenak, A., Foster, I., Kesselman, C., Salisbury, C., Tuecke, S.: The Data Grid: Towards and Architecture for the Distributed Management and Analysis of Large Scientific Data Sets. Journal of Network and Computer Applications 23(3), 187–200 (2000)CrossRefGoogle Scholar
  6. 6.
    Ranganathan, K., Foster, I.: Design and Evaluation of Dynamic Replication Strategies for a High-Performance Data Grid Google Scholar
  7. 7.
    Holtman, K., Stockinger, H.: Building a Large Location Table to Find Replicas of Physics Objects. In: Proc. of CHEP 2000, Padova, Italy (February 2000)Google Scholar
  8. 8.
    Chervenak, A.L., Palavalli, N., Bharathi, S., Kesselman, C., Schwartzkopf, R.: Performance and Scalability of a Replica Location Service. In: Presented at High Performance Distributed Computing Conference (HPDC-13), Honolulu, HI (June 2004)Google Scholar
  9. 9.
    Bhagwan, R., Moore, D., Savage, S., Voelker, G.M.: Replication Strategies for Highly Available Peer-to-Peer StorageGoogle Scholar
  10. 10.
    Dabek, F., Kaashoek, M., Karger, D., Morris, R., Stoica, I.: Wide-area cooperative storage with cfs. In: Proceedings of the 18th ACM Symposium on Operating System Principles (SOSP) (2001)Google Scholar
  11. 11.
    Aggarwal, C.C., Yu, P.S.: On disk caching of web objects in proxy servers. In: Proc. Int’l. Conf. Info and Knowledge Management, CIKM 1997, Las Vegas, Nevada, pp. 238–245 (1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Tan Zhipeng
    • 1
  • Feng Dan
    • 1
  1. 1.Key Laboratory of Data Storage SystemMinistry of Education, School of Computer, Huazhong University of Science and TechnologyWuhanChina

Personalised recommendations